Somehow missed this one: "Reasoning-aware Dense Retrieval Models". Achieves comparable results to ReasonIR w/ a fraction of the training data. Way to go @negin_rahimi and collaborators!
RaDeR: Reasoning-aware Dense Retrieval Models
@DEBRUPD30132796 et al. introduce a set of reasoning-based dense retrieval models trained with data from mathematical problem solving using LLMs, which generalize effectively to diverse reasoning tasks.
📝https://t.co/BXXG3Ku8sy
✨ New Paper ✨
Deep dive on demonstrations to enhance LLM-based passage ranking 🚀 insights for pointwise ranking using query likelihood 🚀
https://t.co/KLga6EEx19
ACM has recently learned of concerns regarding statements made in the past by Jeffrey Ullman, one of this year’s Turing Award recipients. These statements do not reflect the views of ACM.
It's crazy to have presented my @ictir2020 paper at 5am!!! Our paper "Learning to Rank Entities for Set Expansion from Unstructured Data" w/ @Negin_Rahimi, @huang_zhiqi and @jallan_umass can be found at https://t.co/JsDM2RZRh2
In this work we rethink entity set expansion as a learning-to-rank problem. We limit ourselves to expanding only from plain text such that there would be more useful downstream applications such as KBC. We propose data and model to complete this task!
@KittyDesbrow Katherine, I have an important message about (definitely considerable) wealth inherited to you in a country that u probably don't know much about. (Please be aware that u may have incomplete or wrong information)
I can provide u with detailed information privately